---
title: "Directus agent readiness score: 64/100 · Agentrail"
description: "The website’s strongest area is discovery by agents, with its developer resources and brand name discoverable, but it lacks a published OpenAPI spec and WebMCP support."
canonical: "https://www.agentrail.co/agent-readiness/directus.io?h=39TR3BRCCF6VH005"
---

Full report

## See what each check found, and how to fix it.

Evidence, step-by-step fixes and your score over time, for your own site.

[Get started →](https://app.agentrail.co/login?utm%5Fsource=agentrail.co&utm%5Fmedium=website&utm%5Fcampaign=agent-readiness%2Fdirectus.io&utm%5Fcontent=company-report)

Free to start. No card.

Usability

23 to fix

- OAuth 2.0 supportRequiredHow to fix →
- Scoped permissionsRecommendedHow to fix →
- Agent onboarding frictionRecommendedHow to fix →
- Web Bot Auth directoryEmergingHow to fix →

Fixes unlock with the full report

Where the score comes from

58 of 90 points

How directus.io scores on each of the four questions agents ask.

Discovery18/20

Access20/30

Usability20/40

Paymentsnot scored yet

Strongest

### Discovery

ARD entry validity and Wikipedia / Wikidata entity presence are missing.

18/20

Most to gain

### Usability

OAuth 2.0 support, Scoped permissions, and 13 more are missing.

20/40

Most to gain

### Access

Content without JavaScript, JSON-LD structured data, and 5 more are missing.

20/30

Not scored yet

### Payments ( bonus )

Counts when scoring opens.

—

Agent path

## How an agent moved through the site

We asked an agent a question about directus.ioand recorded every request it made.

**D**directus.ioAnsweredRan Nov 20, 2026

Question

I want to start using directus.io (directus.io). Find its setup and getting-started guide.

6

Steps

3m 19s

Duration

6

Pages opened

1

Failed

Every address the agent typed itself loaded. Every link it followed loaded.

1. 1directus.io /Named in the question _→_ **Didn’t load · 301**
2. 2directus.comA link on a page it read _→_ **Read**
3. 3directus.com/startA link on a page it read _→_ **Read**
4. 4directus.com/docsA link on a page it read _→_ **Read**
5. 5directus.com/docs/getting-started/overviewTyped by the agent _→_ **Read**
6. 6directus.com/docs/getting-started/create-a-projectTyped by the agent _→_ **Read**

6/6 steps

StepsHow it found itCame back as

Step 6 of 6

`directus.com/docs/getting-started/create-a-project · not directus.io`

How it got here

Typed by the agent

Response

200

Came back as

Markdown

83%

Pages that loaded

50%

Followed site links

100%

Read as markdown

How it found each page

Named in the question**1**

A link on a page it read**3**

Typed by the agent**2**

A search result**0**

What it reached

Home page**Never reached**

Pricing**Never reached**

Docs**Never reached**

Its answer

Answers aren’t shown publicly

See what agents answer about your own site.

Run agents on your site and read every answer, with every page they opened.

[Get started →](https://app.agentrail.co/login?utm%5Fsource=agentrail.co&utm%5Fmedium=website&utm%5Fcampaign=agent-readiness%2Fdirectus.io&utm%5Fcontent=journey-answer)

Free to start. No card.

Every check

139checks

- Passed**35**
- To fix**24**
- Not in the score**80**

59 checks count toward the score. The other 80 are tracked for later.

Discovery18 of 201 to fix1 partly7 passed

Wikipedia / Wikidata entity presenceRecommended0 / 4

ARD entry validityRecommended0 / 2

ARD discoveryRequired1 / 1

Developer resource discoverabilityRecommended4 / 4

Brand name discoverabilityRequired3 / 3

robots.txt AI crawler policyRequired1 / 1

Listed in MCP registriesRecommended3 / 3

NPM/PyPI SDK packageRecommended1 / 1

Homepage not hidden from searchRecommended1 / 1

\+ 6 checks not in the score

AI Catalog discoveryEmergingNot counted

ARD trust manifestEmergingNot counted

Agent platform configsEmergingNot counted

Agent Plugins manifestEmergingNot counted

Registry brandingEmergingNot counted

ChatGPT app listedRecommendedNot counted

Access20 of 305 to fix2 partly15 passed

JSON-LD structured dataRequired0 / 2

Agent instruction / when-to-useRequired0 / 1

JSON-LD entity linking (sameAs)Recommended0 / 1

Organization schema completenessRecommended0 / 1

OpenAPI spec publishedRequired0 / 8

Content without JavaScriptRequired3.3 / 5

Content behind authRecommended0.5 / 1

Sitemap existsRequired1 / 1

Not blocked by bot detectionRequired2 / 2

robots.txt agent-user policyRequired1 / 1

llms.txt existsRequired1 / 1

llms.txt formattingRecommended2 / 2

Pricing info accessibleRequired3 / 3

Public API/docs linked from homepageRequired4 / 4

Metadata completenessRequired1 / 1

Trust anchor pagesRequired1 / 1

llms.txt links resolveRecommended2 / 2

Redirect hygieneRecommended1 / 1

Page token budgetRecommended1 / 1

Developer portalRecommended5 / 5

Markdown content negotiation (acceptmarkdown.com)Recommended1 / 1

Agent crawler reachabilityRecommended1 / 1

\+ 18 checks not in the score

Agent discovery fileEmergingNot counted

Agent Skills index conformance (v0.2.0)EmergingNot counted

A2A / agent-cardEmergingNot counted

Listed on skills.shEmergingNot counted

pricing.md existsEmergingNot counted

NLWeb Schema FeedsEmergingNot counted

MCP well-known discoveryEmergingNot counted

HTTP Link headers (RFC 8288)EmergingNot counted

Markdown URL fallbackEmergingNot counted

Modular llms.txt per product areaEmergingNot counted

Skills.sh skill qualityEmergingNot counted

Markdown alternate linkEmergingNot counted

Markdown frontmatter metadataEmergingNot counted

Code fence validityEmergingNot counted

API catalog (RFC 9727)EmergingNot counted

Markdown agent docsEmergingNot counted

Bot-UA markdown servingEmergingNot counted

Content starts near the topEmergingNot counted

Usability20 of 4014 to fix1 partly13 passed

OAuth 2.0 supportRequired0 / 5

Scoped permissionsRecommended0 / 5

OAuth Protected Resource metadata (RFC 9728)Required0 / 2

Rate limit response headersRecommended0 / 2

Idempotency-Key supportRecommended0 / 3

REST typed error modelRecommended0 / 3

REST async-job patternRecommended0 / 2

MCP tool annotationsRecommended0 / 3

Sandbox / test environmentRecommended0 / 2

MCP resources exposedRecommended0 / 3

API schema complexity analysisRecommended0 / 2

Function calling compatibilityRecommended0 / 2

MCP server instructionsRecommended0 / 1

MCP tool output schemasRecommended0 / 3

Agent onboarding frictionRecommended1 / 2

MCP tool descriptionsRecommended4 / 4

MCP parameter schemasRecommended3 / 3

MCP server identityRecommended1 / 1

MCP tool listingRecommended3 / 3

MCP tool namingRecommended2 / 2

Public API with reachable endpointsRequired8 / 8

MCP server / manifestRequired10 / 10

MCP error handlingRecommended2 / 2

MCP modern transportRecommended1 / 1

JSON error responsesRequired3 / 3

CLI tool availableRecommended3 / 3

Agent-friendly 404sRecommended2 / 2

MCP tools are distinguishableRecommended2 / 2

\+ 51 checks not in the score

MCP auth mechanismRecommendedNot counted

MCP OAuth metadataRecommendedNot counted

MCP PKCE S256 supportRecommendedNot counted

Web Bot Auth directoryEmergingNot counted

auth.md existsEmergingNot counted

auth.md structureEmergingNot counted

auth.md walkthrough simulationEmergingNot counted

Agent auth discovery metadataEmergingNot counted

Agent auth WWW-Authenticate hintEmergingNot counted

agent\_auth endpoints reachableEmergingNot counted

WebMCP supportRequiredNot counted

REST versioning / deprecation policyRecommendedNot counted

REST pagination patternRecommendedNot counted

NLWeb /ask endpointEmergingNot counted

NLWeb streaming supportEmergingNot counted

REST response schema coverageRecommendedNot counted

MCP server-card.jsonEmergingNot counted

Product + docs MCP coverageRecommendedNot counted

GraphQL typed error modelRecommendedNot counted

GraphQL versioning / deprecation policyRecommendedNot counted

GraphQL pagination patternRecommendedNot counted

GraphQL async-job patternRecommendedNot counted

GraphQL schema description coverageRecommendedNot counted

Accessible document structureEmergingNot counted

Native interactive controlsEmergingNot counted

Accessible names on controlsEmergingNot counted

Form control labelingEmergingNot counted

Accessibility-tree injection safety (bonus)EmergingNot counted

MCP Apps supportRecommendedNot counted

A2UI / generative UI supportEmergingNot counted

MCP Apps UI qualityRecommendedNot counted

MCP App view reachableRecommendedNot counted

MCP App view CSPRecommendedNot counted

MCP resource qualityRecommendedNot counted

MCP Apps checkout viewEmergingNot counted

WebMCP schema validityRecommendedNot counted

WebMCP schema detailRecommendedNot counted

WebMCP real toolsRecommendedNot counted

WebMCP entry pointRecommendedNot counted

WebMCP tool namesRecommendedNot counted

WebMCP read-only hintsRecommendedNot counted

WebMCP honest hintsRecommendedNot counted

WebMCP untrusted content hintRecommendedNot counted

WebMCP consequential hintRecommendedNot counted

WebMCP coverageRecommendedNot counted

Personal Agent Protocol discovery fileEmergingNot counted

PAP issuer bindingEmergingNot counted

PAP sign-in and extension configEmergingNot counted

PAP API and agent entriesEmergingNot counted

PAP endpoints reject unauthenticated agentsEmergingNot counted

PAP agrees with ARD and auth.mdEmergingNot counted

PaymentsNot scored yet

\+ 5 checks not in the score

MPP payment protocolRequiredNot counted

x402 payment protocolRequiredNot counted

UCP - Universal Commerce ProtocolRequiredNot counted

ACP - Agentic Commerce ProtocolRequiredNot counted

Agent wallet checkoutRequiredNot counted
